nvidia-kimi-vision
miladnoo 作
Web & Frontend Development概要
Analyze images using NVIDIA Kimi K2.5 vision model via NVIDIA NIM API.
説明
このスキルでできること
Analyzes images using the Kimi K2.5 multimodal model via NVIDIA NIM API. Useful for adding vision capabilities to agents or models that lack native image understanding. Supports PNG, JPG, JPEG, and WebP formats.
Gives any agent or model image understanding without requiring a native vision model, using NVIDIA NIM's free tier for fast inference.
使いどころ
- Extract text from a screenshot
- Describe what's in a photo
- Analyze a meme or diagram
- Identify objects in an image
- Add vision to a non-vision LLM workflow
ワークフロー例
User asks: What does this receipt say?
- 1
Receives the image path and prompt from the user
- 2
Checks for an NVIDIA NIM API key in ~/.config/nvidia-kimi-api-key
- 3
Calls the Kimi K2.5 model via NVIDIA NIM API with the image and prompt
- 4
Returns the extracted text from the receipt
Itemized list of purchases and totals read from the receipt image
要件
- NVIDIA NIM API key from build.nvidia.com (free tier available)
インストール
clawhub install miladnoo/nvidia-kimi-visionCLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。